There are several problems with the current annotations (AnnotateRWLockCreate and friends):
- they don't fully support deadlock detection (we need a hook _before_ mutex lock)
- they don't support insertion of random artificial delays to perturb execution (again we need a hook _before_ mutex lock)
- they don't support setting extended mutex attributes like read/write reentrancy (only "linker init" was bolted on)
- they don't support setting mutex attributes if a mutex don't have a "constructor" (e.g. static, Java, Go mutexes)
- they don't ignore synchronization inside of lock/unlock operations which leads to slowdown and false negatives
The new annotations solve of the above problems. See tsan_interface.h for the interface specification and comments.
Reviewed in https://reviews.llvm.org/D31093
llvm-svn: 298809
Fixes crash reported in:
https://bugs.chromium.org/p/v8/issues/detail?id=4995
The problem is that we don't have a processor in a free interceptor
during thread exit.
The crash was introduced by introduction of Processors.
However, previously we silently leaked memory which wasn't any better.
llvm-svn: 268782
Race deduplication code proved to be a performance bottleneck in the past if suppressions/annotations are used, or just some races left unaddressed. And we still get user complaints about this:
https://groups.google.com/forum/#!topic/thread-sanitizer/hB0WyiTI4e4
ReportRace already has several layers of caching for racy pcs/addresses to make deduplication faster. However, ReportRace still takes a global mutex (ThreadRegistry and ReportMutex) during deduplication and also calls mmap/munmap (which take process-wide semaphore in kernel), this makes deduplication non-scalable.
This patch moves race deduplication outside of global mutexes and also removes all mmap/munmap calls.
As the result, race_stress.cc with 100 threads and 10000 iterations become 30x faster:
before:
real 0m21.673s
user 0m5.932s
sys 0m34.885s
after:
real 0m0.720s
user 0m23.646s
sys 0m1.254s
http://reviews.llvm.org/D12554
llvm-svn: 246758
The optimization is two-fold:
First, the algorithm now uses SSE instructions to
handle all 4 shadow slots at once. This makes processing
faster.
Second, if shadow contains the same access, we do not
store the event into trace. This increases effective
trace size, that is, tsan can remember up to 10x more
previous memory accesses.
Perofrmance impact:
Before:
[ OK ] DISABLED_BENCH.Mop8Read (2461 ms)
[ OK ] DISABLED_BENCH.Mop8Write (1836 ms)
After:
[ OK ] DISABLED_BENCH.Mop8Read (1204 ms)
[ OK ] DISABLED_BENCH.Mop8Write (976 ms)
But this measures only fast-path.
On large real applications the speedup is ~20%.
Trace size impact:
On app1:
Memory accesses : 1163265870
Including same : 791312905 (68%)
on app2:
Memory accesses : 166875345
Including same : 150449689 (90%)
90% of filtered events means that trace size is effectively 10x larger.
llvm-svn: 209897
Make vector clock operations O(1) for several important classes of use cases.
See comments for details.
Below are stats from a large server app, 77% of all clock operations are handled as O(1).
Clock acquire : 25983645
empty clock : 6288080
fast from release-store : 14917504
contains my tid : 4515743
repeated (fast) : 2141428
full (slow) : 2636633
acquired something : 1426863
Clock release : 2544216
resize : 6241
fast1 : 197693
fast2 : 1016293
fast3 : 2007
full (slow) : 1797488
was acquired : 709227
clear tail : 1
last overflow : 0
Clock release store : 3446946
resize : 200516
fast : 469265
slow : 2977681
clear tail : 0
Clock acquire-release : 820028
llvm-svn: 204656
Intercept and sanitize arguments passed to printf functions in ASan and TSan
(don't do this in MSan for now). The checks are controlled by runtime flag
(off by default for now).
Patch http://llvm-reviews.chandlerc.com/D2480 by Yuri Gribov!
llvm-svn: 199729
The annotations are AnnotateIgnoreSyncBegin/End,
may be useful to ignore some infrastructure synchronization
that introduces lots of false negatives.
llvm-svn: 192355
LibIgnore allows to ignore all interceptors called from a particular set
of dynamic libraries. LibIgnore remembers all "called_from_lib" suppressions
from the provided SuppressionContext; finds code ranges for the libraries;
and checks whether the provided PC value belongs to the code ranges.
Also make malloc and friends interceptors use SCOPED_INTERCEPTOR_RAW instead of
SCOPED_TSAN_INTERCEPTOR, because if they are called from an ignored lib,
then must call our internal allocator instead of libc malloc.
llvm-svn: 191897
This reverts commit r187788.
The test case is unreliable (as the test may be run in a situation in
which it has no affinity with cpu0). This can be recommitted with a more
reliable test - possibly using CPU_COUNT != 0 instead (I wasn't entirely
sure that a process was guaranteed to have at least one affinity, though
it seems reasonable, or I'd have made the change myself).
llvm-svn: 187841
Dmitry Vyukov